πŸ‘‹ Home πŸ“š Library πŸ“‘ Posts πŸ““ Wiki πŸ—‚οΈ Tables

Search

Pull for commands
πŸ“‘ Posts 2023 01 10 5

Posts from January 10, 2023

Casey Gollan
Casey Gollan
β™₯ liked @gsuberland@chaos.social 3 years ago
Graham Sutherland / Polynomial G
Graham Sutherland / Polynomial @gsuberland@chaos.social · 3y 🐘

@reboot @SnowDerg @eevee if you did this with a small corpus it would be laughably bad. but because it has been trained on a metric crapton of human conversation on a huge variety of topics, there's a disparity of sourcing data between what it has "seen" and what you have seen. so even though the actual correlation and generation processes are ultimately simplistic, the huge amount of data it can draw from makes it *seem* convincing.


Casey Gollan
β™₯ liked @gsuberland@chaos.social 3 years ago
Graham Sutherland / Polynomial G
Graham Sutherland / Polynomial @gsuberland@chaos.social · 3y 🐘

@reboot @SnowDerg @eevee this is why I call it a word recommendation algorithm. you give it a prompt and it correlates that with wording that it has seen before from its massive training corpus of human conversations. from there it can launder those words through a generative language model that "follows" the linguistic structures it has been trained on, to produce a paragraph of text.


Casey Gollan
β™₯ liked @gsuberland@chaos.social 3 years ago
Graham Sutherland / Polynomial G
Graham Sutherland / Polynomial @gsuberland@chaos.social · 3y 🐘

@reboot @SnowDerg @eevee LLM = large language model

I find it important to not use the term "understanding" in this context because the model is *not* understanding anything. It can *mimic* understanding through correlative processes, for sure, but the distinction is important.


Casey Gollan
β™₯ liked @gsuberland@chaos.social 3 years ago
Graham Sutherland / Polynomial G
Graham Sutherland / Polynomial @gsuberland@chaos.social · 3y 🐘

@reboot @SnowDerg @eevee I'm probably not the right person to talk about it in deep detail since the gory innards of LLMs and autoregressive models aren't my wheelhouse. Someone did post a good article on LLMs the other day but I can't spot it.

I'd recommend searching online for an explainer but unfortunately every single one I found on the first page of Google was a bust due to gushingly anthropomorphising the model in a way that falsely implied an ability to develop understanding.


Casey Gollan
β™₯ liked @flancian@social.coop 3 years ago
To #Flancia and beyond! T
To #Flancia and beyond! @flancian@social.coop · 3y 🐘

[[topic maps]]
---
RT @gardenfelder
Topic Maps are among the original "knowledge graph" platforms, with some features which go beyond what has been available. They have evolved beyond the XML Topic Maps ISO standard. https://twitter.com/flancian/status/1612402672946089984
https://twitter.com/gardenfelder/status/1612480283517026305

Twitter@flancian@social.coop on Twitterβ€œ@gardenfelder Awesome! I ran into topic maps while researching for projects/efforts in the space of the Agora this weekend. What would be a good canonical description of what they are/could be, and what they are used for? If you have one.”